Purpose Path planning is a fundamental and significant issue in robotics research, especially for the legged robots, since it is the core technology for robots to complete complex tasks such as autonomous navigation and exploration. The purpose of this paper is to propose a path planning and tracking framework for the autonomous navigation of hexapod robots. Design/methodology/approach First, a hexapod robot called Hexapod-Mini is briefly introduced. Then a path planning algorithm based on improved A* is proposed, which introduces the artificial potential field (APF) factor into the evaluation function to generate a safe and collision-free initial path. Then we apply a turning point optimization based on the greedy algorithm, which optimizes the number of turns of the path. And a fast-turning trajectory for hexapod robot is proposed, which is applied to path smoothing. Besides, a model predictive control-based motion tracking controller is used for path tracking. Findings The simulation and experiment results show that the framework can generate a safe, fast, collision-free and smooth path, and the author’s Hexapod robot can effectively track the path that demonstrates the performance of the framework. Originality/value The work presented a framework for autonomous path planning and tracking of hexapod robots. This new approach overcomes the disadvantages of the traditional path planning approach, such as lack of security, insufficient smoothness and an excessive number of turns. And the proposed method has been successfully applied to an actual hexapod robot.

No abstract

Financial time series prediction has always been a tricky problem due to the uncertainty in the market. It has attracted attention from industry to academia. In recent years, deep learning has shown excellent performance in many different fields. More and more researchers try to apply deep learning on financial markets. In this paper, the complete modeling process of price movement prediction is introduced. Based on high frequency data Limit Order Books, an improved deep learning model combining the local feature extraction ability of Convolutional Neural Network (CNN) with the sequential feature extraction ability of Long Short-Term Memory (LSTM) is proposed and evaluated on RB dominant contracts in the China futures market. Based on the experimental results, it is concluded that our model’s performance on prediction is better than that of single CNN and LSTM models. Through back testing, trading based on the predicted results of the proposed model can yield significantly more returns than other models.

No abstract